© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 24126
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences that begin with "How does" or "How do."

    oai_token-act-pair · gpt-3.5-turbo

    questions or inquiries about processes or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hao
    -0.78
    ãĥĩãĤ£
    -0.73
    vic
    -0.68
    tto
    -0.68
    bsp
    -0.68
    xxxxxxxx
    -0.67
    HB
    -0.67
    ca
    -0.65
    Hug
    -0.65
    cca
    -0.64
    POSITIVE LOGITS
     reconcil
    0.80
    ?]
    0.75
     reconcile
    0.73
     coping
    0.68
     fix
    0.67
     reacting
    0.65
     Lanka
    0.64
     educated
    0.64
     retribution
    0.64
     interpreting
    0.63
    Activations Density 0.042%

    No Known Activations